import ipywidgets as widgets
from ipywidgets import interact, interact_manual

import pandas as pd

wine_data = pd.read_csv('winequality-white.csv')

wine_data.head()

wine_data.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')

wine_data.tail()

len(wine_data)

4898

wine_data.describe()

distplot¶

import seaborn as sns
import matplotlib.pyplot as plt

wine_data = pd.read_csv('winequality-white.csv')
wine_data.columns = ['fixed_acidity', 'volatile_acidity', 'citric_acid', 'residual_sugar',
                     'chlorides', 'free_sulfur_dioxide', 'total_sulfur_dioxide', 'density',
                     'pH', 'sulphates', 'alcohol', 'quality']

wine_data.tail(10)

plt.hist(wine_data.alcohol)

(array([ 37., 808., 969., 761., 765., 625., 427., 368., 110.,  28.]),
 array([ 8.  ,  8.62,  9.24,  9.86, 10.48, 11.1 , 11.72, 12.34, 12.96,
        13.58, 14.2 ]),
 <a list of 10 Patch objects>)

# histogram bars KDE:gaussian kernel density estimate.
sns.distplot(wine_data.alcohol, kde=True)

<matplotlib.axes._subplots.AxesSubplot at 0x1a77b2c8208>

around 40% have alcohol content = 9.3

f, ax = plt.subplots(figsize=(15, 5))
sns.distplot(wine_data.alcohol, kde=True)

<matplotlib.axes._subplots.AxesSubplot at 0x1a77b3b8b38>

f, ax = plt.subplots(figsize=(15, 5))
sns.distplot(wine_data.alcohol, kde=False, rug=True, bins=200)

<matplotlib.axes._subplots.AxesSubplot at 0x1a77b5d20f0>

rug: Whether to draw a rugplot on the support axis.

bins control granularity of the bars , bins = more size -> you can analyse the data more deep

f, ax = plt.subplots(figsize=(15, 5))
# most of the rug distribution is clustered around centre
sns.rugplot(wine_data.alcohol, height=0.75)

<matplotlib.axes._subplots.AxesSubplot at 0x1a77b5cc5f8>

f, ax = plt.subplots(figsize=(15, 5))
sns.distplot(wine_data.alcohol, kde=True, rug=True, hist=False)

<matplotlib.axes._subplots.AxesSubplot at 0x1a77be83160>

shade the Kernal density estimation area¶

f, ax = plt.subplots(figsize=(15, 5))
sns.set(color_codes=True)
sns.kdeplot(wine_data.alcohol, shade=True, color='r')

<matplotlib.axes._subplots.AxesSubplot at 0x1a77c2570f0>

plotting KDE with various bandwidth that fits the original data¶

f, ax = plt.subplots(figsize=(15, 5))
sns.kdeplot(wine_data.alcohol)
sns.kdeplot(wine_data.alcohol, bw=0.04, label='bw =0.04 ')
sns.kdeplot(wine_data.alcohol, bw=0.2, label='bw =0.2 ')
sns.kdeplot(wine_data.alcohol, bw=2, label='bw =2 ')
sns.kdeplot(wine_data.alcohol, bw=5, label='bw =5 ')

<matplotlib.axes._subplots.AxesSubplot at 0x1a77c2c5828>

the more erratic the plot is the less generic information it provides¶

Joint Plots along with univariate distribution¶

sns.jointplot(x=wine_data.free_sulfur_dioxide, y=wine_data.total_sulfur_dioxide, xlim={
              0, 150}, ylim={0, 400}, alpha=0.2)  # ALPHA STILL WORKS HERE

<seaborn.axisgrid.JointGrid at 0x1a77c772c50>

Hexbin Plots - Histogram representation of bivariate plot¶

the problem here in jointplot is at the middle we can not decide the relationship between wine_data.free_sulfur_dioxide wine_data.total_sulfur_dioxide ; solution to this is plotting Hexbin plot with Hue variations¶

how dark and how light a perticular point is represents the height of histogram at intersection¶

sns.jointplot(x=wine_data.free_sulfur_dioxide,              y=wine_data.total_sulfur_dioxide, kind='hex', xlim={0, 100}, ylim={0, 200})

<seaborn.axisgrid.JointGrid at 0x1a77c7357f0>

KDE curves for bivariate distribution¶

sns.jointplot(x=wine_data.free_sulfur_dioxide,
              y=wine_data.total_sulfur_dioxide, kind='kde', xlim={0, 80}, ylim={0, 300})

<seaborn.axisgrid.JointGrid at 0x1a77ca967f0>

f, ax = plt.subplots(figsize=(8, 5))
sns.kdeplot(wine_data.free_sulfur_dioxide, wine_data.total_sulfur_dioxide)
sns.rugplot(wine_data.free_sulfur_dioxide, color='g', height=0.05)
sns.rugplot(wine_data.total_sulfur_dioxide,
            color='b', height=0.05, vertical=True)
plt.xlim(-20, 100)
plt.ylim(-50, 400)

(-50, 400)

plot bivariate relationships between every pair of columns in a dataset¶

# sns.pairplot(wine_data, height=3) # rn this it takes a lot of time

sns.pairplot(wine_data, height=3, vars=[
             'fixed_acidity', 'chlorides', 'sulphates', 'alcohol', 'quality'], diag_kind='kde')

<seaborn.axisgrid.PairGrid at 0x1a77d16eb38>

pairwise regressions¶

sns.pairplot(wine_data, height=3, vars=[
             'chlorides', 'sulphates', 'quality'], kind='reg')

<seaborn.axisgrid.PairGrid at 0x1a77ee865c0>

g = sns.PairGrid(wine_data, height=3, vars=['chlorides', 'sulphates', 'quality'])
g.map(plt.scatter)

<seaborn.axisgrid.PairGrid at 0x1a77f911550>

dont you think it is stupid to plot a univariate varaible against itself... ok lets do one thing let's plot KDE for diagonal and scatter for non diagonal plots¶

g = sns.PairGrid(wine_data, vars=['chlorides','sulphates', 'alcohol'], hue='quality')
g.map_offdiag(plt.scatter)
g.map_diag(sns.kdeplot)
plt.legend(loc=2)

<matplotlib.legend.Legend at 0x1a77fe86438>

Now how about tuning PairGrid even further map_upper map_lower map_diag¶

g = sns.PairGrid(wine_data, vars=['chlorides', 'sulphates', 'alcohol'])

g.map_diag(sns.kdeplot)
g.map_upper(sns.scatterplot)
g.map_lower(sns.regplot)

<seaborn.axisgrid.PairGrid at 0x1a701628940>

Howabout using PairGrid with x_vars and y_vars differet¶

g = sns.PairGrid(wine_data, x_vars=['chlorides', 'sulphates', 'fixed_acidity'], y_vars=['alcohol'])
g.map(plt.scatter)

# g.map_diag(sns.kdeplot)
# g.map_upper(sns.scatterplot)
# g.map_lower(sns.regplot)

<seaborn.axisgrid.PairGrid at 0x1a701b7ba58>

g = sns.PairGrid(wine_data, x_vars=['chlorides', 'sulphates', 'fixed_acidity'], y_vars=['alcohol'])
g.map(sns.scatterplot)  # sns looks more beautiful

<seaborn.axisgrid.PairGrid at 0x1a701e0d978>

# sns.pairplot(wine_data, height=3, vars=['fixed_acidity','chlorides','sulphates', 'quality'], hue = 'pH')

Heatmaps¶

corrmat = wine_data.corr()
f, ax = plt.subplots(figsize=(10, 10))
# sns.heatmap(corrmat, vmin = -0.9, vmax=0.95, square = True, annot= True, fmt='.2f', cmap='summer' )
sns.heatmap(corrmat, annot=True, fmt='0.2f', square=True)

<matplotlib.axes._subplots.AxesSubplot at 0x1a701ecf940>

lmplots and regplots for regression¶

sns.lmplot(x='residual_sugar', y='density', data=wine_data, height=7, aspect=2)

<seaborn.axisgrid.FacetGrid at 0x1a701c1b898>

when MSE is low CI is narrow and whereever the MSE is high CI-confidence Interval is High¶

categorical variable with discrete values¶

sns.lmplot(x='quality', y='alcohol', data=wine_data)

<seaborn.axisgrid.FacetGrid at 0x1a7024a9390>

hard to see individual data points so add some jittering - regression line is not affected by jittering¶

sns.lmplot(x='quality', y='alcohol', data=wine_data, x_jitter=.2)

<seaborn.axisgrid.FacetGrid at 0x1a702705940>

import numpy as np
sns.lmplot(x='quality', y='alcohol', data=wine_data, x_estimator=np.mean)

<seaborn.axisgrid.FacetGrid at 0x1a7022fec88>

Higher quality means higher alcohol content¶

# sns.lmplot(x='pH',y='fixed_acidity', data= wine_data, row='quality', hue='alcohol') # Fixed_acidity vs pH in each quality category with hue= alcohol : needs tuning

# sns.lmplot(x='pH',y='fixed_acidity', data= wine_data, col='quality', hue='alcohol') # Fixed_acidity vs pH in each quality category with hue= alcohol

regplot¶

regplot is similar to lmplot but accepts inputs in various forms such as numpy arrays pandas series dataframe variable references¶

regplot is axis level v/s lmplot is figure level¶

lmplot is more powerful and operates at higher level at matplotlib¶

sns.regplot(wine_data.alcohol, wine_data.density, color='0')

<matplotlib.axes._subplots.AxesSubplot at 0x1a7027f7eb8>

f, ax = plt.subplots(figsize=(12, 5))
sns.regplot(x=wine_data.residual_sugar, y=wine_data.density,
            ax=ax)  # controlling size and shape

<matplotlib.axes._subplots.AxesSubplot at 0x1a70285fc88>

joint plots also plots regression if kind is specified as 'reg'¶

sns.jointplot(x=wine_data.free_sulfur_dioxide, y=wine_data.total_sulfur_dioxide, xlim={0, 150}, ylim={0, 400}, kind='reg')

<seaborn.axisgrid.JointGrid at 0x1a70282f2e8>

sns.pairplot(wine_data, x_vars=['fixed_acidity','citric_acid', 'chlorides'], y_vars=['alcohol'], kind='reg', height=8, aspect=1)

<seaborn.axisgrid.PairGrid at 0x1a703abef98>

CATEGORICAL AND MULTIPANEL DATA¶

f, ax = plt.subplots(figsize=(15, 5))
sns.stripplot(x='quality', y='alcohol', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a703fabe48>

sns.swarmplot(x='quality', y='alcohol', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a7043a5438>

sns.dogplot() # haha

BOX PLOT¶

sns.boxplot(x='quality', y='alcohol', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a7044a48d0>

wiskers are mostly 1.5 times inter quantile ; any data outside this range is represented as outlier seperately¶

VIOLIN PLOT mit distribution probability¶

sns.violinplot(x='quality', y='alcohol', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a7047d04e0>

The curved boundaries represents KDE , violin plot also shows mode ; violin plots can also be plotted relative to counts of individual data¶

sns.violinplot(x='quality', y='alcohol', data=wine_data, scale='count')

<matplotlib.axes._subplots.AxesSubplot at 0x1a704b188d0>

here you can scale the width with respect to number of counts of each categorical observation¶

sns.violinplot(x='quality', y='alcohol', data=wine_data,scale='count', inner='stick')

<matplotlib.axes._subplots.AxesSubplot at 0x1a704a33ef0>

scaled thickly closed lines suggest there are many samples in our data with quality 6 and at alcohol level 11.5¶

COMBINING SWARM AND VIOLIN PLOTS¶

sns.violinplot(x='quality', y='alcohol', data=wine_data)
sns.swarmplot(x='quality', y='alcohol', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a709101dd8>

STATISTICAL ESTIMATION¶

sns.barplot(x='quality', y='pH', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a708979550>

sns.countplot(x='alcohol', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a7089f98d0>

sns.countplot(x='alcohol', data=wine_data, color='m', palette='Greens_d')
plt.xticks(rotation=90)

(array([  0,   1,   2,   3,   4,   5,   6,   7,   8,   9,  10,  11,  12,
         13,  14,  15,  16,  17,  18,  19,  20,  21,  22,  23,  24,  25,
         26,  27,  28,  29,  30,  31,  32,  33,  34,  35,  36,  37,  38,
         39,  40,  41,  42,  43,  44,  45,  46,  47,  48,  49,  50,  51,
         52,  53,  54,  55,  56,  57,  58,  59,  60,  61,  62,  63,  64,
         65,  66,  67,  68,  69,  70,  71,  72,  73,  74,  75,  76,  77,
         78,  79,  80,  81,  82,  83,  84,  85,  86,  87,  88,  89,  90,
         91,  92,  93,  94,  95,  96,  97,  98,  99, 100, 101, 102]),
 <a list of 103 Text xticklabel objects>)

Number of wines at every alcohollevel¶

POINT PLOT¶

A point plot represents an estimate of central tendency for a numeric variable by the position of scatter plot points and provides some indication of the uncertainty around that estimate using error bars.¶

sns.pointplot(x='quality', y='pH', data=wine_data)

<matplotlib.axes._subplots.AxesSubplot at 0x1a7022f1390>

Observe how the alcohol content varies with the ph and quality of wine¶

BOX PLOT¶

sns.boxplot(data=wine_data, orient='h')

<matplotlib.axes._subplots.AxesSubplot at 0x1a704a16630>

Seaborn is a powerful visualization library built on top of matplotlib ; tightly integrated with PyData stack and makes production ready plots¶

Facet grids in Seaborn¶

titanic = pd.read_csv('titanic.csv')

titanic.head()

g = sns.FacetGrid(titanic, col='Pclass') # try plotting with out mapping and see !

g = sns.FacetGrid(titanic, col='Survived')
g.map(plt.hist, 'Pclass', color='k')

<seaborn.axisgrid.FacetGrid at 0x1a7029fde48>

Plotting bivariate data¶

g = sns.FacetGrid(titanic, col='Survived', height=8)
g.map(plt.scatter, 'Age', 'Fare')

<seaborn.axisgrid.FacetGrid at 0x1a70aea7198>

g = sns.FacetGrid(titanic, col='Survived', height=8, hue='Sex')
g.map(plt.scatter, 'Age', 'Fare', alpha=0.99)  # alpha is the opacity
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x1a70b438588>

g = sns.FacetGrid(titanic, col='Survived', height=8, hue='Sex')
g.map(plt.bar, 'Age', 'Fare', alpha=0.99)  # alpha is the opacity
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x1a70b4389e8>

g = sns.FacetGrid(titanic, col='Survived', row='Pclass', height=8, hue='Sex')
g.map(plt.bar, 'Age', 'Fare', alpha=0.99)  # alpha is the opacity
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x1a70ada8208>

g = sns.FacetGrid(titanic, col='Survived', row='Pclass', height=8, hue='Sex')
g.map(sns.barplot, 'Age', 'Fare')

c:\python37\lib\site-packages\seaborn\axisgrid.py:715: UserWarning: Using the barplot function without specifying `order` is likely to produce an incorrect plot.
  warnings.warn(warning)

<seaborn.axisgrid.FacetGrid at 0x1a70da390b8>

g = sns.FacetGrid(titanic, col='Survived', row='Pclass', height=8, hue='Sex')
g.map(plt.scatter, 'Age', 'Fare', alpha=0.99)  # alpha is the opacity
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x1a70df7d630>

# How about changing some colors
h = {"male": 'b', "female": 'r'}
g = sns.FacetGrid(titanic, col='Survived', row='Pclass',height=8, hue='Sex', palette=h)
g.map(plt.scatter, 'Age', 'Fare', alpha=0.99)  # alpha is the opacity
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x1a70ece2f28>

NOW HOW ABOUT SOME FINE TUNInG!!!¶

g = sns.FacetGrid(titanic, col='Survived', height=8, col_wrap=4)
g.map(sns.barplot, 'Age', 'Fare')

<seaborn.axisgrid.FacetGrid at 0x1a70ef77080>

g = sns.FacetGrid(titanic, col='Survived', row='Pclass', height=8, hue='Sex')
g.map(sns.barplot, 'Age', 'Fare', color='#334488',
      edgecolor='red', lw=.5)  # color is a hex parameter
plt.xticks(rotation=90)
# giving some white space and horizontal spacing
g.fig.subplots_adjust(wspace=0.3, hspace=0.5)

Changing labels¶

g = sns.FacetGrid(titanic, col='Survived', row='Pclass', height=8)
g.map(sns.barplot, 'Age', 'Fare', color='#334488',
      edgecolor='red', lw=.5)  # color is a hex parameter
plt.xticks(rotation=90)
# giving some white space and horizontal spacing
g.fig.subplots_adjust(wspace=0.3, hspace=0.5)
g.set_axis_labels('Age of Passengers', 'Fare of each Passenger')

<seaborn.axisgrid.FacetGrid at 0x1a7140d92e8>

is this bar graph showing frequency of fares? no !! it is just giving one farevalue for each bucket of age; work on it later now!¶

Customizing the yticks¶

g = sns.FacetGrid(titanic, col='Survived', height=8, hue='Sex')
g.map(sns.scatterplot, 'Age', 'Fare')  # color is a hex parameter
# giving some white space and horizontal spacing
g.fig.subplots_adjust(wspace=0.3, hspace=0.5)
g.set_axis_labels('Age of Passengers', 'Fare of each Passenger')
g.set(yticks=[0, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500])

<seaborn.axisgrid.FacetGrid at 0x1a7125ef9e8>

xlim and ylim - limit your x and y ticks¶

g = sns.FacetGrid(titanic, col='Survived', height=5,
                  hue='Sex', xlim=(0, 16), ylim=(100, 500))
g.map(sns.scatterplot, 'Age', 'Fare')  # color is a hex parameter
# giving some white space and horizontal spacing
g.fig.subplots_adjust(wspace=0.3, hspace=0.5)
g.set_axis_labels('Age of Passengers', 'Fare of each Passenger')

<seaborn.axisgrid.FacetGrid at 0x1a712825ba8>

this is function inbulit argument method to restrict our x and y ticks¶

g = sns.FacetGrid(titanic, col='Survived', height=5, hue='Sex')
g.map(sns.scatterplot, 'Age', 'Fare')  # color is a hex parameter
# giving some white space and horizontal spacing
g.fig.subplots_adjust(wspace=0.3, hspace=0.5)
g.set_axis_labels('Age of Passengers', 'Fare of each Passenger')
g.set(xlim=(0, 16), ylim=(100, 500))

<seaborn.axisgrid.FacetGrid at 0x1a712875908>

Machine learning bicycle data set¶

bike = pd.read_csv('bike_sharing_daily.csv')

bike.head()

bike.columns

Index(['instant', 'dteday', 'season', 'yr', 'mnth', 'holiday', 'weekday',
       'workingday', 'weathersit', 'temp', 'atemp', 'hum', 'windspeed',
       'casual', 'registered', 'cnt'],
      dtype='object')

bike.columns = ['instant', 'date', 'season', 'year', 'month', 'holiday', 'weekday',
                'workingday', 'weathersituation', 'temp', 'atemp', 'humidity', 'windspeed',
                'casual_users', 'registered_users', 'cnt']

# bike.cnt.head(200) bike count per day may go above 8000 per day and some days as low as 100 bikes per day

f, ax = plt.subplots(figsize=(15, 5))
sns.set(style="whitegrid")
# sns.set_xticklabels=([0,500,1000,1500,2000,2500,3000,3500,4000,4500,5000,5500,6000,6500,7000,7500,8000,8500,9000])
sns.distplot(bike.cnt, bins=120, kde=False, rug=True, color='k')

<matplotlib.axes._subplots.AxesSubplot at 0x1a7126cd550>

f, ax = plt.subplots(figsize=(15, 5))
sns.set(style="whitegrid")
# sns.set_xticklabels=([0,500,1000,1500,2000,2500,3000,3500,4000,4500,5000,5500,6000,6500,7000,7500,8000,8500,9000])
sns.distplot(bike.cnt, bins=120, kde=True, rug=True, color='k')

<matplotlib.axes._subplots.AxesSubplot at 0x1a712736e48>

# number of bikes hired as a function of day passed
sns.jointplot(bike.instant, bike.cnt, height=8, color='g')

<seaborn.axisgrid.JointGrid at 0x1a7129c1b38>

two peaks in two years¶

sns.jointplot(bike.month, bike.cnt, height=8, color='g')

<seaborn.axisgrid.JointGrid at 0x1a715dd6da0>

monthwise counts; as seen in months 8,9,10 more bicycles are rented¶

season wise rental data¶

sns.jointplot(bike.season, bike.cnt)  # counts are higher in season 3 and 4

<seaborn.axisgrid.JointGrid at 0x1a716583198>

sns.pairplot(bike, height=6, aspect=1.2, x_vars=[
             'temp', 'humidity', 'windspeed'], y_vars='cnt', hue='season')

<seaborn.axisgrid.PairGrid at 0x1a716825780>

Themes and Styles¶

# sns.set_style('darkgrid') # applies to all lines ; affects all plots that follow
# f,ax = plt.subplots(figsize=(15,5))
# sns.scatterplot(bike.cnt)

with sns.axes_style('darkgrid'):  # applies to only this lines
    f, ax = plt.subplots(figsize=(15, 5))
    sns.distplot(bike.cnt)

How to remove spines¶

sns.jointplot(bike.instant, bike.cnt, height=8, color='g')
sns.despine(offset=15, trim=True)

sns.set()

sns.jointplot(bike.instant, bike.cnt, height=8, color='g')

<seaborn.axisgrid.JointGrid at 0x1a716ef27f0>

colors¶

current_palette = sns.color_palette()
sns.palplot(current_palette)

sns.palplot(sns.color_palette('hls', 8))  # hls-> Hue Lightness and Saturation

sns.palplot(sns.hls_palette(n_colors=15, h=.99, l=0.5, s=.99))

sns.choose_colorbrewer_palette('sequential')

[(0.9575547866205305, 0.9575547866205305, 0.9575547866205305),
 (0.9012072279892349, 0.9012072279892349, 0.9012072279892349),
 (0.8328950403690888, 0.8328950403690888, 0.8328950403690888),
 (0.7502191464821223, 0.7502191464821223, 0.7502191464821223),
 (0.6434140715109573, 0.6434140715109573, 0.6434140715109573),
 (0.5387158785082661, 0.5387158785082661, 0.5387158785082661),
 (0.440322952710496, 0.440322952710496, 0.440322952710496),
 (0.342883506343714, 0.342883506343714, 0.342883506343714),
 (0.22329873125720878, 0.22329873125720878, 0.22329873125720878),
 (0.10469819300269129, 0.10469819300269129, 0.10469819300269129)]

sns.choose_colorbrewer_palette('diverging')

[(0.6922722029988467, 0.09227220299884642, 0.16770472895040373),
 (0.8392156862745099, 0.376470588235294, 0.3019607843137253),
 (0.9545559400230679, 0.641753171856978, 0.5057285659361783),
 (0.9921568627450982, 0.8588235294117645, 0.7803921568627449),
 (0.9657054978854286, 0.9672433679354094, 0.9680891964628989),
 (0.8196078431372551, 0.8980392156862745, 0.9411764705882353),
 (0.5664744329104192, 0.7687043444828916, 0.8685121107266438),
 (0.26274509803921564, 0.576470588235294, 0.7647058823529411),
 (0.1272587466359093, 0.39584775086505203, 0.6687427912341407)]

# sequential color plots ;
sns.palplot(sns.color_palette('Blues'))

# sequential color plots ;
sns.palplot(sns.color_palette('Blues_d'))

sns.choose_colorbrewer_palette('sequential')

[(0.9575547866205305, 0.9575547866205305, 0.9575547866205305),
 (0.9012072279892349, 0.9012072279892349, 0.9012072279892349),
 (0.8328950403690888, 0.8328950403690888, 0.8328950403690888),
 (0.7502191464821223, 0.7502191464821223, 0.7502191464821223),
 (0.6434140715109573, 0.6434140715109573, 0.6434140715109573),
 (0.5387158785082661, 0.5387158785082661, 0.5387158785082661),
 (0.440322952710496, 0.440322952710496, 0.440322952710496),
 (0.342883506343714, 0.342883506343714, 0.342883506343714),
 (0.22329873125720878, 0.22329873125720878, 0.22329873125720878),
 (0.10469819300269129, 0.10469819300269129, 0.10469819300269129)]

sns.palplot(sns.color_palette('cubehelix', 12))

sns.palplot(sns.cubehelix_palette(12))  # good for printing

Diverging color palette¶

h = sns.choose_colorbrewer_palette('diverging')

h = sns.choose_colorbrewer_palette('sequential')
g = sns.PairGrid(wine_data, x_vars=['chlorides', 'sulphates', 'fixed_acidity'], y_vars=['alcohol'], hue='pH', palette=h, height=8)
g.map(sns.scatterplot)  # sns looks more beautiful
# g.add_legend()

<seaborn.axisgrid.PairGrid at 0x1a717b2e160>

Aesthetics¶

sns.axes_style()  # current style

{'axes.facecolor': '#EAEAF2',
 'axes.edgecolor': 'white',
 'axes.grid': True,
 'axes.axisbelow': True,
 'axes.labelcolor': '.15',
 'figure.facecolor': 'white',
 'grid.color': 'white',
 'grid.linestyle': '-',
 'text.color': '.15',
 'xtick.color': '.15',
 'ytick.color': '.15',
 'xtick.direction': 'out',
 'ytick.direction': 'out',
 'lines.solid_capstyle': 'round',
 'patch.edgecolor': 'w',
 'image.cmap': 'rocket',
 'font.family': ['sans-serif'],
 'font.sans-serif': ['Arial',
  'DejaVu Sans',
  'Liberation Sans',
  'Bitstream Vera Sans',
  'sans-serif'],
 'patch.force_edgecolor': True,
 'xtick.bottom': False,
 'xtick.top': False,
 'ytick.left': False,
 'ytick.right': False,
 'axes.spines.left': True,
 'axes.spines.bottom': True,
 'axes.spines.right': True,
 'axes.spines.top': True}

sns.set_style('ticks', {'xtick.major.size': 8, 'xtick.color': '.15',
                        'ytick.color': '.85', 'ytick.major.size': 10, 'axes.facecolor': 'm'})

sns.jointplot(bike.instant, bike.cnt, height=8, color='k')

<seaborn.axisgrid.JointGrid at 0x1a716d32940>

sns.set()  # reset everything

sns.jointplot(bike.instant, bike.cnt, height=8, color='k')

<seaborn.axisgrid.JointGrid at 0x1a7183b9390>

printable and seminar contexts¶

sns.set_context('talk')
sns.jointplot(bike.instant, bike.cnt, height=8, color='k')

<seaborn.axisgrid.JointGrid at 0x1a71a9aef98>

sns.set_context('paper')
sns.jointplot(bike.instant, bike.cnt, height=8, color='k')

<seaborn.axisgrid.JointGrid at 0x1a71b530710>

sns.set_context('notebook')
sns.jointplot(bike.instant, bike.cnt, height=8, color='k')

<seaborn.axisgrid.JointGrid at 0x1a71b193c50>

sns.set_context('poster')
sns.jointplot(bike.instant, bike.cnt, height=8, color='k')

<seaborn.axisgrid.JointGrid at 0x1a719c91e80>

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
0	7.0	0.27	0.36	20.7	0.045	45.0	170.0	1.0010	3.00	0.45	8.8	6
1	6.3	0.30	0.34	1.6	0.049	14.0	132.0	0.9940	3.30	0.49	9.5	6
2	8.1	0.28	0.40	6.9	0.050	30.0	97.0	0.9951	3.26	0.44	10.1	6
3	7.2	0.23	0.32	8.5	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6
4	7.2	0.23	0.32	8.5	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
4893	6.2	0.21	0.29	1.6	0.039	24.0	92.0	0.99114	3.27	0.50	11.2	6
4894	6.6	0.32	0.36	8.0	0.047	57.0	168.0	0.99490	3.15	0.46	9.6	5
4895	6.5	0.24	0.19	1.2	0.041	30.0	111.0	0.99254	2.99	0.46	9.4	6
4896	5.5	0.29	0.30	1.1	0.022	20.0	110.0	0.98869	3.34	0.38	12.8	7
4897	6.0	0.21	0.38	0.8	0.020	22.0	98.0	0.98941	3.26	0.32	11.8	6

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
count	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000	4898.000000
mean	6.854788	0.278241	0.334192	6.391415	0.045772	35.308085	138.360657	0.994027	3.188267	0.489847	10.514267	5.877909
std	0.843868	0.100795	0.121020	5.072058	0.021848	17.007137	42.498065	0.002991	0.151001	0.114126	1.230621	0.885639
min	3.800000	0.080000	0.000000	0.600000	0.009000	2.000000	9.000000	0.987110	2.720000	0.220000	8.000000	3.000000
25%	6.300000	0.210000	0.270000	1.700000	0.036000	23.000000	108.000000	0.991723	3.090000	0.410000	9.500000	5.000000
50%	6.800000	0.260000	0.320000	5.200000	0.043000	34.000000	134.000000	0.993740	3.180000	0.470000	10.400000	6.000000
75%	7.300000	0.320000	0.390000	9.900000	0.050000	46.000000	167.000000	0.996100	3.280000	0.550000	11.400000	6.000000
max	14.200000	1.100000	1.660000	65.800000	0.346000	289.000000	440.000000	1.038980	3.820000	1.080000	14.200000	9.000000

	fixed_acidity	volatile_acidity	citric_acid	residual_sugar	chlorides	free_sulfur_dioxide	total_sulfur_dioxide	density	pH	sulphates	alcohol	quality
4888	6.8	0.220	0.36	1.20	0.052	38.0	127.0	0.99330	3.04	0.54	9.2	5
4889	4.9	0.235	0.27	11.75	0.030	34.0	118.0	0.99540	3.07	0.50	9.4	6
4890	6.1	0.340	0.29	2.20	0.036	25.0	100.0	0.98938	3.06	0.44	11.8	6
4891	5.7	0.210	0.32	0.90	0.038	38.0	121.0	0.99074	3.24	0.46	10.6	6
4892	6.5	0.230	0.38	1.30	0.032	29.0	112.0	0.99298	3.29	0.54	9.7	5
4893	6.2	0.210	0.29	1.60	0.039	24.0	92.0	0.99114	3.27	0.50	11.2	6
4894	6.6	0.320	0.36	8.00	0.047	57.0	168.0	0.99490	3.15	0.46	9.6	5
4895	6.5	0.240	0.19	1.20	0.041	30.0	111.0	0.99254	2.99	0.46	9.4	6
4896	5.5	0.290	0.30	1.10	0.022	20.0	110.0	0.98869	3.34	0.38	12.8	7
4897	6.0	0.210	0.38	0.80	0.020	22.0	98.0	0.98941	3.26	0.32	11.8	6

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	373450	8.0500	NaN	S

	instant	dteday	season	mnth	weekday	workingday	weathersit	temp	atemp	hum	windspeed	casual	registered	cnt
0	1	2011-01-01	1	1	6	0	2	0.344167	0.363625	0.805833	0.160446	331	654	985
1	2	2011-01-02	1	1	0	0	2	0.363478	0.353739	0.696087	0.248539	131	670	801
2	3	2011-01-03	1	1	1	1	1	0.196364	0.189405	0.437273	0.248309	120	1229	1349
3	4	2011-01-04	1	1	2	1	1	0.200000	0.212122	0.590435	0.160296	108	1454	1562
4	5	2011-01-05	1	1	3	1	1	0.226957	0.229270	0.436957	0.186900	82	1518	1600

distplot¶

shade the Kernal density estimation area¶

plotting KDE with various bandwidth that fits the original data¶

the more erratic the plot is the less generic information it provides¶

Joint Plots along with univariate distribution¶

Hexbin Plots - Histogram representation of bivariate plot¶

the problem here in jointplot is at the middle we can not decide the relationship between wine_data.free_sulfur_dioxide wine_data.total_sulfur_dioxide ; solution to this is plotting Hexbin plot with Hue variations¶

how dark and how light a perticular point is represents the height of histogram at intersection¶

KDE curves for bivariate distribution¶

plot bivariate relationships between every pair of columns in a dataset¶

pairwise regressions¶

dont you think it is stupid to plot a univariate varaible against itself... ok lets do one thing let's plot KDE for diagonal and scatter for non diagonal plots¶

Now how about tuning PairGrid even further map_upper map_lower map_diag¶

Howabout using PairGrid with x_vars and y_vars differet¶

Heatmaps¶

lmplots and regplots for regression¶

when MSE is low CI is narrow and whereever the MSE is high CI-confidence Interval is High¶

categorical variable with discrete values¶

hard to see individual data points so add some jittering - regression line is not affected by jittering¶

Higher quality means higher alcohol content¶

regplot¶

regplot is similar to lmplot but accepts inputs in various forms such as numpy arrays pandas series dataframe variable references¶

regplot is axis level v/s lmplot is figure level¶

lmplot is more powerful and operates at higher level at matplotlib¶

joint plots also plots regression if kind is specified as 'reg'¶

CATEGORICAL AND MULTIPANEL DATA¶

BOX PLOT¶

wiskers are mostly 1.5 times inter quantile ; any data outside this range is represented as outlier seperately¶

VIOLIN PLOT mit distribution probability¶

The curved boundaries represents KDE , violin plot also shows mode ; violin plots can also be plotted relative to counts of individual data¶

here you can scale the width with respect to number of counts of each categorical observation¶

scaled thickly closed lines suggest there are many samples in our data with quality 6 and at alcohol level 11.5¶

COMBINING SWARM AND VIOLIN PLOTS¶

STATISTICAL ESTIMATION¶

Number of wines at every alcohollevel¶

POINT PLOT¶

A point plot represents an estimate of central tendency for a numeric variable by the position of scatter plot points and provides some indication of the uncertainty around that estimate using error bars.¶

Observe how the alcohol content varies with the ph and quality of wine¶

BOX PLOT¶

Seaborn is a powerful visualization library built on top of matplotlib ; tightly integrated with PyData stack and makes production ready plots¶

Facet grids in Seaborn¶

Plotting bivariate data¶

NOW HOW ABOUT SOME FINE TUNInG!!!¶

Changing labels¶

is this bar graph showing frequency of fares? no !! it is just giving one farevalue for each bucket of age; work on it later now!¶

Customizing the yticks¶

xlim and ylim - limit your x and y ticks¶

this is function inbulit argument method to restrict our x and y ticks¶

Machine learning bicycle data set¶

two peaks in two years¶

monthwise counts; as seen in months 8,9,10 more bicycles are rented¶

season wise rental data¶

Themes and Styles¶

How to remove spines¶

colors¶

Diverging color palette¶

Aesthetics¶

printable and seminar contexts¶

continued!!!!!¶